Methods and systems for personalized image generation

Abstract

A method and a system for personalized image generation are provided. The method includes: determining a facial description text specified by a user; generating, based on the facial description text, a facial image by using a generative algorithm; obtaining a first dressing effect image of a target garment, the first dressing effect image presenting a wearing effect of the target garment on a digital model; and generating a second dressing effect image of the target garment by performing a fusion operation on the facial image and the first dressing effect image, the second dressing effect image presenting a wearing effect of the target garment on a fused digital model. The provided solution not only enables the rapid, high-quality generation of garment images but also ensures that the fused images maintain feature consistency, meeting users' personalized display preferences.

What is claimed is: 
     
         1 . A method for personalized image generation, comprising:
 obtaining an image including a model element and a garment element;   displaying an element editing interface; the element editing interface includes at least one editing region corresponding to at least one of the garment element, the model element or a scene element;   receiving an user input via the editing region;   determining at least one adjustment instruction using the user input;   modifying the image according to the adjustment instruction.   
     
     
         2 . The method of  claim 1 , wherein the receiving a user input via the editing region includes:
 obtaining a scene element.   
     
     
         3 . The method of  claim 2 , wherein the modifying the image according to the adjustment instruction includes:
 encoding the image to obtain an encoded image;   modifying the encoded image by adding the scene element to obtain a modified image;   decoding the modified image to obtain a finished image.   
     
     
         4 . The method of  claim 2 , wherein the scene element includes one or more elements of the following: a color tone, a layout, matching of the scene. 
     
     
         5 . The method of  claim 1 , wherein further comprising: parsing the garment element and the model element in the image;
 the modifying the image according to the adjustment instruction includes: modifying the image by adjusting the garment element and/or the model element to obtain a finished image.   
     
     
         6 . The method of  claim 5 , wherein the modifying the image by adjusting the garment element and/or the model element to obtain a finished image includes:
 encoding the image to obtain an encoded image;   modifying the encoded image by adjusting the garment element and/or the model element to obtain a modified image;   decoding the modified image to obtain the finished image.   
     
     
         7 . The method of  claim 5 , wherein the model element includes one or more elements of the following: a skin color, an expression, a posture, a facial contour, a hair style, a body shape, a makeup;
 the garment element includes one or more elements of the following: an outline, a texture, a color, a style of the garment.   
     
     
         8 . The method of  claim 1 , wherein the obtaining an image including a model element and a garment element includes:
 generating a 3D model by performing 3D modeling on a garment and a model, and obtaining the image by rendering the 3D model; or   obtaining the image input by a user.   
     
     
         9 . The method of  claim 8 , wherein the generating a 3D model by performing 3D modeling on a garment and a model includes:
 when generating the 3D model, pre-setting a scene compatible with the garment and the model to generate the 3D model including the scene.   
     
     
         10 . The method of  claim 1 , wherein
 the element editing interface includes one or more element options and/or one or more attribute options;   the method further comprising: receiving the element option and/or the attribute option selected by a user, and determining the at least one adjustment instruction according to the element option and/or the attribute option selected by the user.   
     
     
         11 . The method of  claim 1 , wherein the modifying the image according to the adjustment instruction includes:
 encoding the image to obtain an initial feature vector of the image;   modifying a portion of feature values in the initial feature vector, based on the adjustment instruction, to form a target feature vector;   decoding the target feature vector to obtain a finished image.   
     
     
         12 . A non-transitory computer readable medium, comprising executable instructions that, when executed by an electronic device, directs the electronic device to perform actions of:
 obtaining an image including a model element and a garment element;   displaying an element editing interface; the element editing interface includes at least one editing region corresponding to at least one of the garment element, the model element or a scene element;   receiving an user input via the editing region;   determining at least one adjustment instruction using the user input;   modifying the image according to the adjustment instruction.   
     
     
         13 . A system, comprising:
 at least one storage device storing a set of instructions; and   at least one processor configured to communicate with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to direct the system to perform operations including:   obtaining an image including a model element and a garment element;   displaying an element editing interface; the element editing interface includes at least one editing region corresponding to at least one of the garment element, the model element or a scene element;   receiving an user input via the editing region;   determining at least one adjustment instruction using the user input;   modifying the image according to the adjustment instruction.   
     
     
         14 . The system of  claim 13 , wherein the receiving a user input via the editing region includes:
 obtaining a scene element.   
     
     
         15 . The system of  claim 14 , wherein modifying the image according to the adjustment instruction includes:
 encoding the image to obtain an encoded image;   modifying the encoded image by adding the scene element to obtain a modified image;   decoding the modified image to obtain a finished image.   
     
     
         16 . The system of  claim 14 , wherein the scene element includes one or more elements of the following: a color tone, a layout, matching of the scene. 
     
     
         17 . The system of  claim 14 , wherein the model element includes one or more elements of the following: a skin color, an expression, a posture, a facial contour, a hair style, a body shape, a makeup;
 the garment element includes one or more elements of the following: an outline, a texture, a color, a style of the garment.   
     
     
         18 . The system of  claim 13 , wherein the obtaining an image including a model element and a garment element includes:
 generating a 3D model by performing 3D modeling on a garment and a model, and obtaining the image by rendering the 3D model; or   obtaining the image input by a user.   
     
     
         19 . The system of  claim 18 , wherein the generating a 3D model by performing 3D modeling on a garment and a model includes:
 when generating the 3D model, pre-setting a scene compatible with the garment and the model to generate the 3D model including the scene.   
     
     
         20 . The system of  claim 13 , wherein the element editing interface includes one or more element options and/or one or more attribute options;
 the operations further comprising: receiving the element option and/or the attribute option selected by a user, and determining the at least one adjustment instruction according to the element option and/or the attribute option selected by the user.